RedHatAI/Llama-3.1-8B-Instruct-NVFP4

from vllm import LLM, SamplingParams
from transformers import AutoTokenizer

model_id = "RedHatAI/Meta-Llama-3.1-8B-Instruct-NVFP4"
number_gpus = 1

sampling_params = SamplingParams(temperature=0.6, top_p=0.9, max_tokens=256)

tokenizer = AutoTokenizer.from_pretrained(model_id)

messages = [
    {"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
    {"role": "user", "content": "Who are you?"},
]

prompts = tokenizer.apply_chat_template(messages, add_generation_prompt=True, tokenize=False)

llm = LLM(model=model_id, tensor_parallel_size=number_gpus)

outputs = llm.generate(prompts, sampling_params)

generated_text = outputs[0].outputs[0].text
print(generated_text)

from datasets import load_dataset
from transformers import AutoModelForCausalLM, AutoTokenizer

from llmcompressor import oneshot
from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
from llmcompressor.utils import dispatch_for_generation

MODEL_ID = "meta-llama/Meta-Llama-3-8B-Instruct"

# Load model.
model = AutoModelForCausalLM.from_pretrained(MODEL_ID, torch_dtype="auto")
tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)

DATASET_ID = "HuggingFaceH4/ultrachat_200k"
DATASET_SPLIT = "train_sft"

# Select number of samples. 512 samples is a good place to start.
# Increasing the number of samples can improve accuracy.
NUM_CALIBRATION_SAMPLES = 512
MAX_SEQUENCE_LENGTH = 2048

# Load dataset and preprocess.
ds = load_dataset(DATASET_ID, split=f"{DATASET_SPLIT}[:{NUM_CALIBRATION_SAMPLES}]")
ds = ds.shuffle(seed=42)

def preprocess(example):
    return {
        "text": tokenizer.apply_chat_template(
            example["messages"],
            tokenize=False,
        )
    }

ds = ds.map(preprocess)

# Tokenize inputs.
def tokenize(sample):
    return tokenizer(
        sample["text"],
        padding=False,
        max_length=MAX_SEQUENCE_LENGTH,
        truncation=True,
        add_special_tokens=False,
    )

ds = ds.map(tokenize, remove_columns=ds.column_names)

# Configure the quantization algorithm and scheme.
# In this case, we:
#   * quantize the weights to fp4 with per group 16 via ptq
#   * calibrate a global_scale for activations, which will be used to
#       quantize activations to fp4 on the fly
smoothing_strength = 0.5
recipe = [
    SmoothQuantModifier(smoothing_strength=smoothing_strength),
    QuantizationModifier(
        ignore=["re:.*lm_head.*"],
        config_groups={
            "group_0": {
                "targets": ["Linear"],
                "weights": {
                    "num_bits": 4,
                    "type": "float",
                    "strategy": "tensor_group",
                    "group_size": 16,
                    "symmetric": True,
                    "observer": "mse",
                },
                "input_activations": {
                    "num_bits": 4,
                    "type": "float",
                    "strategy": "tensor_group",
                    "group_size": 16,
                    "symmetric": True,
                    "dynamic": "local",
                    "observer": "minmax",
                },
            }
        },
    )
]

# Save to disk in compressed-tensors format.
SAVE_DIR = MODEL_ID.rstrip("/").split("/")[-1] + "-NVFP4"

# Apply quantization.
oneshot(
    model=model,
    dataset=ds,
    recipe=recipe,
    max_seq_length=MAX_SEQUENCE_LENGTH,
    num_calibration_samples=NUM_CALIBRATION_SAMPLES,
    output_dir=SAVE_DIR,
)

print("\n\n")
print("========== SAMPLE GENERATION ==============")
dispatch_for_generation(model)
input_ids = tokenizer("Hello my name is", return_tensors="pt").input_ids.to("cuda")
output = model.generate(input_ids, max_new_tokens=100)
print(tokenizer.decode(output[0]))
print("==========================================\n\n")

model.save_pretrained(SAVE_DIR, save_compressed=True)
tokenizer.save_pretrained(SAVE_DIR)

lm_eval \
  --model vllm \
  --model_args pretrained="RedHatAI/Meta-Llama-3.1-8B-Instruct-NVFP4",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True,enforce_eager=True \
  --tasks mmlu_llama \
  --apply_chat_template \
  --fewshot_as_multiturn \
  --batch_size auto

lm_eval \
  --model vllm \
  --model_args pretrained="RedHatAI/Meta-Llama-3.1-8B-Instruct-NVFP4",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True,enforce_eager=True \
  --tasks mmlu_cot_llama \
  --apply_chat_template \
  --fewshot_as_multiturn \
  --batch_size auto

lm_eval \
  --model vllm \
  --model_args pretrained="RedHatAI/Meta-Llama-3.1-8B-Instruct-NVFP4",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True,enforce_eager=True \
  --tasks arc_challenge_llama \
  --apply_chat_template \
  --batch_size auto

lm_eval \
  --model vllm \
  --model_args pretrained="RedHatAI/Meta-Llama-3.1-8B-Instruct-NVFP4",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True,enforce_eager=True \
  --tasks gsm8k_llama \
  --apply_chat_template \
  --fewshot_as_multiturn \
  --batch_size auto

lm_eval \
  --model vllm \
  --model_args pretrained="RedHatAI/Meta-Llama-3.1-8B-Instruct-NVFP4",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True,enforce_eager=True \
  --tasks hellaswag \
  --apply_chat_template \
  --fewshot_as_multiturn \
  --batch_size auto

lm_eval \
  --model vllm \
  --model_args pretrained="RedHatAI/Meta-Llama-3.1-8B-Instruct-NVFP4",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True,enforce_eager=True \
  --tasks winogrande \
  --apply_chat_template \
  --fewshot_as_multiturn \
  --batch_size auto

lm_eval \
  --model vllm \
  --model_args pretrained="RedHatAI/Meta-Llama-3.1-8B-Instruct-NVFP4",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True,enforce_eager=True \
  --tasks truthfulqa \
  --apply_chat_template \
  --fewshot_as_multiturn \
  --batch_size auto

lm_eval \
  --model vllm \
  --model_args pretrained="RedHatAI/Meta-Llama-3.1-8B-Instruct-NVFP4",dtype=auto,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True,enforce_eager=True\
  --apply_chat_template \
  --fewshot_as_multiturn \
  --tasks leaderboard \
  --batch_size auto

lm_eval \
  --model vllm \
  --model_args pretrained="RedHatAI/Meta-Llama-3.1-8B-Instruct-NVFP4",dtype=auto,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True,enforce_eager=True\
  --apply_chat_template \
  --fewshot_as_multiturn \
  --tasks humaneval_64_instruct \
  --batch_size auto